Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 18429
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements, particularly those related to functions and statements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ostavi
    -1.00
    Personensuche
    -0.96
    SharedCtor
    -0.91
    SourceChecksum
    -0.85
     betweenstory
    -0.83
    省市镇
    -0.82
    oredCriteria
    -0.82
    elemField
    -0.80
    MigrationBuilder
    -0.79
     kaarangay
    -0.78
    POSITIVE LOGITS
    acc
    0.51
     moth
    0.49
    flo
    0.46
    ignon
    0.44
    ச்
    0.44
    enein
    0.44
    ign
    0.44
    </em>
    0.44
    crimin
    0.43
     linear
    0.43
    Activations Density 0.062%

    No Known Activations